mindspore.ops.softshrink

mindspore.ops.softshrink(input, lambd=0.5)

Soft Shrink activation function. Calculates the output according to the input elements.

The formula is defined as follows:

$$\begin{array}{r}\text{SoftShrink}(x)=\{\begin{array}{ll}x-\lambda ,& \text{ if }x>\lambda \\ x+\lambda ,& \text{ if }x<-\lambda \\ 0,& \text{ otherwise }\end{array}\end{array}$$

SoftShrink Activation Function Graph:

Parameters

• input (Tensor) –

  The input of Soft Shrink. Supported dtypes:

  • Ascend: float16, float32, bfloat16.

  • CPU/GPU: float16, float32.

• lambd (number, optional) – The threshold $\lambda$ defined by the Soft Shrink formula. It should be greater than or equal to 0, default: 0.5 .

Returns

Tensor, has the same data type and shape as the input input.

Raises

• TypeError – If lambd is not a float, int or bool.

• TypeError – If input is not a tensor.

• TypeError – If dtype of input is not float16, float32 or bfloat16.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor
>>> from mindspore import ops
>>> import numpy as np
>>> x = Tensor(np.array([[ 0.5297,  0.7871,  1.1754], [ 0.7836,  0.6218, -1.1542]]), mindspore.float32)
>>> output = ops.softshrink(x)
>>> print(output)
[[ 0.02979  0.287    0.676  ]
[ 0.2837   0.1216  -0.6543 ]]